© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 14690
    Prev
    Next
    INDEX
    Explanations

    tunnels, galleries, storage, be designed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tart
    -0.10
     Ku
    -0.10
     tornado
    -0.09
     Dum
    -0.09
     Tart
    -0.09
     erosion
    -0.09
     stair
    -0.09
     Waters
    -0.09
     Hier
    -0.08
     aggregator
    -0.08
    POSITIVE LOGITS
     tunnel
    0.27
     Tunnel
    0.23
     tun
    0.21
    unnel
    0.19
    _tunnel
    0.17
     boring
    0.17
     tunnels
    0.16
     lining
    0.14
     ÄijÃło
    0.14
     bored
    0.13
    Activations Density 0.019%

    No Known Activations